3DMorph: Single-Image-Guided Local 3D Shape Editing and Morphing
This work addresses the lack of intuitive, local geometry editing tools for general 3D meshes, which is a bottleneck for 3D design workflows.
3DMorph introduces a training-free framework for local 3D shape editing guided by a single edited image, enabling automatic region localization and 2D-to-3D transfer while preserving unmodified areas. It outperforms state-of-the-art methods on the new Delta3D benchmark.
Despite recent progress in 3D generation, intuitive editing of existing shapes remains limited. Unlike images, which benefit from well-established inpainting tools, general 3D objects such as meshes still lack simple and effective methods for local shape editing. Existing approaches are often global, domain-specific, require complex user interaction, or focus on appearance (color and texture) rather than geometry. We introduce 3DMorph, a training-free framework for single-image-guided local 3D shape editing and morphing. Given an edited image showing a desired shape modification, our method automatically localizes the relevant 3D region and transfers 2D modifications to 3D while preserving unmodified areas. 3DMorph also enables intermediate shape generation between the original and edited objects, facilitating design exploration. To benchmark editing quality, we introduce Delta3D, an image-guided local 3D editing benchmark with paired ground-truth edits. Experimental results show that 3DMorph translates intuitive 2D edits into 3D, outperforming state-of-the-art generative and editing methods.